Inter-frame contextual modelling for visual speech recognition.
Adrian PassJi MingPhilip HannaJianguo ZhangDarryl StewartPublished in: ICIP (2010)
Keyphrases
- inter frame
- visual speech recognition
- motion estimation
- video sequences
- bit rate
- video frames
- hidden markov models
- lip reading
- intra frame
- prediction error
- compressed domain
- speech recognition
- quadtree
- dynamic textures
- video codec
- visual speech
- video coding
- multiscale
- high quality
- macroblock
- bitstream
- image sequences
- moving objects
- image quality
- image compression
- spatio temporal